© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 7737
    Prev
    Next
    INDEX
    Explanations

    phrases including the name "Hannity."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Ann" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lda
    -0.77
    ngth
    -0.69
    EStreamFrame
    -0.65
     logger
    -0.65
    rero
    -0.64
     membrane
    -0.63
    nces
    -0.63
    graded
    -0.62
    senal
    -0.60
    dden
    -0.59
    POSITIVE LOGITS
    ihil
    1.33
    ihilation
    1.30
    ibal
    1.23
    iversary
    1.22
    abis
    1.18
    igans
    1.01
    ounce
    1.00
    apolis
    0.99
    unciation
    0.97
    enberg
    0.97
    Activations Density 0.027%

    No Known Activations